Suzhou Electric Appliance Research Institute
期刊號(hào): CN32-1800/TM| ISSN1007-3175

Article retrieval

文章檢索

首頁 >> 文章檢索 >> 文章瀏覽排名

基于LIESN的光伏功率預(yù)測(cè)研究

來源:電工電氣發(fā)布時(shí)間:2018-04-19 09:19 瀏覽次數(shù):667
基于LIESN的光伏功率預(yù)測(cè)研究
 
孫鵬1,張依強(qiáng)1,焦程煒2
(1 國(guó)網(wǎng)山東省電力公司菏澤供電公司,山東 菏澤 274000;2 國(guó)網(wǎng)山東省電力公司萊蕪供電公司,山東 萊蕪 271100)
 
    摘 要:為了光伏功率預(yù)測(cè)結(jié)果有更好的準(zhǔn)確性與普適性,提出基于泄漏積分型回聲狀態(tài)網(wǎng)絡(luò)(LIESN) 的具有在線學(xué)習(xí)功能的預(yù)測(cè)方法。在回聲狀態(tài)網(wǎng)絡(luò)(ESN) 中引入泄漏積分型神經(jīng)元,增強(qiáng)儲(chǔ)備池的短期記憶能力;分析了LIESN的參數(shù)對(duì)其光伏功率預(yù)測(cè)性能的影響,得到優(yōu)化后的預(yù)測(cè)模型;利用最小二乘在線學(xué)習(xí)算法對(duì)模型實(shí)施訓(xùn)練,得到最終的在線學(xué)習(xí)LIESN預(yù)測(cè)模型。實(shí)例證明,該算法可完成復(fù)雜的建模且適用于多種天氣情況,預(yù)測(cè)精度優(yōu)于BP神經(jīng)網(wǎng)絡(luò)、經(jīng)典ESN及LIESN模型,驗(yàn)證了方法的有效性。
    關(guān)鍵詞:回聲狀態(tài)網(wǎng)絡(luò);泄漏積分;神經(jīng)元;光伏功率預(yù)測(cè);在線學(xué)習(xí)
    中圖分類號(hào):TM615     文獻(xiàn)標(biāo)識(shí)碼:A     文章編號(hào):1007-3175(2018)04-0018-06
 
Online-Learning PV Power Forecasting Based on Leaky-Integrator ESN
 
SUN Peng1, ZHANG Yi-qiang1, JIAO Cheng-wei2
(1 Heze Power Supply Company, Heze 274000, China; 2 Laiwu Power Supply Company, Laiwu 2711 00, China)
 
    Abstract: In order to enhance computing accuracy and universality of photovoltaic (PV) power forecasting, this paper proposed a online-learning method based on leaky-integrator echo state network(LIESN). Leaky-integrator neurons were introduced to plain ESN and the short-term memory ability was promoted. The impact of parameters of LIESN on PV power forecasting performance was analyzed and an optimized model was obtained. The model was trained by least squares online learning algorithm and final forecasting was obtained. By practical examples, complicated model can be established and applied to various weather conditions. The forecasting accuracy was superior to the BP neural network and plain ESN and the validity of proposed method is testified.
    Key words: echo state network; leaky-integarator; neurons; photovoltaic power forecasting; online learning
 
參考文獻(xiàn)
[1] FERNANDEZ-JIMENEZ L A, MUNOZ-JIMENEZ A, FALCES A, et al. Short-term power forecasting system for photovoltaic plants[J]. Renewable Energy,2012,44(4):311-317.
[2] 龔鶯飛,魯宗相,喬穎,等. 光伏功率預(yù)測(cè)技術(shù)[J]. 電力系統(tǒng)自動(dòng)化,2016,40(4):140-151.
[3] 陳昌松,段善旭,殷進(jìn)軍. 基于神經(jīng)網(wǎng)絡(luò)的光伏陣列發(fā)電預(yù)測(cè)模型的設(shè)計(jì)[J]. 電工技術(shù)學(xué)報(bào),2009,24(9):153-158.
[4] 李鵬梅,臧傳治,王侃侃. 基于相似日和神經(jīng)網(wǎng)絡(luò)的光伏發(fā)電預(yù)測(cè)[J]. 可再生能源,2013,31(10):1-4.
[5] 黃磊,舒杰,姜桂秀,等. 基于多維時(shí)間序列局部支持向量回歸的微網(wǎng)光伏發(fā)電預(yù)測(cè)[J]. 電力系統(tǒng)自動(dòng)化,2014,38(5):19-24.
[6] SHI J, LEE W J, LIU Y, et al.Forecasting Power Output of Photovoltaic Systems Based on Weather Classification and Support Vector Machines[J].IEEE Transactions on Industry Applications,2012,48(3):1064-1069.
[7] LI Y T, SU Y, SHU L J.An ARMAX model for forecasting the power output of a grid connected photovoltaic system[J].Renewable Energy,2014,66(6):78-89.
[8] JAYAWARDENE I, VENAYAGAMOORTHY G K.Comparisonof echo state network and extreme learning machine for PV power prediction[C]//2014 IEEE Symposium on Computational Intelligence Applications in Smart Grid (CIASG),2014.
[9] JAEGER H. The “echo state” approach to analysing and training recurrent neural networks[J].Uberwachtes Lernen,2001:1-47.
[10] JAEGER H, LUKOSEVICIUS M, DAN P, et al. Optimization and applications of echo state networks with leaky-integrator neurons[J]. Neural Networks,2007,20(3):335-352.
[11] 羅熊,黎江,孫增圻. 回聲狀態(tài)網(wǎng)絡(luò)的研究進(jìn)展[J].北京科技大學(xué)學(xué)報(bào),2012,34(2):217-222.
[12] 彭宇,王建民,彭喜元. 基于回聲狀態(tài)網(wǎng)絡(luò)的時(shí)間序列預(yù)測(cè)方法研究[J]. 電子學(xué)報(bào),2010,38(B2):148-154.
[13] 倫淑嫻,林健,姚顯雙. 基于小世界回聲狀態(tài)網(wǎng)的時(shí)間序列預(yù)測(cè)[J]. 自動(dòng)化學(xué)報(bào),2015,41(9):1669-1679.
[14] LUN S X, YAO X S, QI H Y, HU H F. A novel model of leaky integrator echo state network for time-series prediction[J].Neurocomputing,2015,159(1):58-66.
[15] 李軍,岳文琦. 基于泄漏積分型回聲狀態(tài)網(wǎng)絡(luò)的軟測(cè)量動(dòng)態(tài)建模方法及應(yīng)用[J]. 化工學(xué)報(bào),2014,65(10):4004-4014.
[16] 張浩然, 汪曉東. 回歸最小二乘支持向量機(jī)的增量和在線式學(xué)習(xí)算法[J]. 計(jì)算機(jī)學(xué)報(bào),2006,29(3):400-406.
[17] 郭振凱,宋召青,毛劍琴. 一種改進(jìn)的在線最小二乘支持向量機(jī)回歸算法[J]. 控制與決策,2009,24(1):145-148.
[18] 葉林,陳政,趙永寧,等. 基于遺傳算法—模糊徑向基神經(jīng)網(wǎng)絡(luò)的光伏發(fā)電功率預(yù)測(cè)模型[J]. 電力系統(tǒng)自動(dòng)化,2015,39(16):16-22.